IEEE Trans Pattern Anal Mach Intell. 2022 Feb;44(2):622-635. doi: 10.1109/TPAMI.2019.2929036. Epub 2022 Jan 7.
The large pose variations and misalignment errors exhibited by person images significantly increase the difficulty of person Re-Identification (ReID). Existing works commonly apply extra operations like pose estimation, part segmentation, etc., to alleviate those issues and improve the robustness of pedestrian representations. While boosting the ReID accuracy, those operations introduce considerable computational overheads and make the deep models complex and hard to tune. To chase a more efficient solution, we propose a Part-Guided Representation (PGR) composed of Pose Invariant Feature (PIF) and Local Descriptive Feature (LDF), respectively. We call PGR "Part-Guided" because it is trained and supervised by local part cues. Specifically, PIF approximates a pose invariant representation inferred by pose estimation and pose normalization. LDF focuses on discriminative body parts by approximating a representation learned with body region segmentation. In this way, extra pose extraction is only introduced during the training stage to supervise the learning of PGR, but is not required during the testing stage for feature extraction. Extensive comparisons with recent works on five widely used datasets demonstrate the competitive accuracy and efficiency of PGR.
人像的大幅度姿势变化和对位错误显著增加了人像重识别（ReID）的难度。现有的工作通常应用额外的操作，如姿势估计、部位分割等，以减轻这些问题并提高行人表示的鲁棒性。虽然这些操作提高了 ReID 的准确性，但它们引入了相当大的计算开销，使得深度模型复杂且难以调整。为了追求更高效的解决方案，我们提出了由姿态不变特征（PIF）和局部描述特征（LDF）分别组成的部分引导表示（PGR）。我们称 PGR 为“部分引导”，因为它是通过局部部分线索进行训练和监督的。具体来说，PIF 通过姿态估计和姿态归一化推断出一种姿态不变的表示。LDF 通过近似使用身体区域分割学习的表示来关注有区别的身体部位。这样，在训练阶段只引入额外的姿势提取来监督 PGR 的学习，而在测试阶段不需要进行特征提取。在五个广泛使用的数据集上与最近的工作进行的广泛比较证明了 PGR 的竞争准确性和效率。
